YepAPI

Command Palette

Search for a command to run...

StepFunText Generation/v1/ai/chat

Step 3.5 Flash

Access Step 3.5 Flash through one API key. StepFun's fast model.

StepFun's fast inference model. Budget-friendly Chinese provider with 262K context window.

No credit card required. Takes 30 seconds.

2,400+

Developers

1.2M+

API calls served

100+

Endpoints

$0.01

Per call

Yep, that's it.

Try it live

Send a message and see Step 3.5 Flash respond in real time.

POST/v1/ai/chat

Maximum tokens in the response.

Real-time tokens

Hit "Send Request" to see the response

Context Window

262K tokens

Max Output

66K tokens

Input Price

$0.14 / 1M tokens

Output Price

$0.42 / 1M tokens

Strengths

Speed

StepFun's fast-inference tier is tuned for low-latency responses on high-throughput workloads.

Cost-effective

At $0.14 per 1M input tokens, it offers budget pricing for high-volume text tasks.

Multilingual

Handles multiple languages, useful for international applications and translation tasks.

Chinese

Built by a Chinese provider with strong Chinese-language understanding and generation.

Quick start

Copy this snippet and start making calls with Step 3.5 Flash.

const res = await fetch('https://api.yepapi.com/v1/ai/chat', {
  method: 'POST',
  headers: {
    'x-api-key': 'YOUR_API_KEY',
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    "model": "stepfun/step-3.5-flash",
    "messages": [
      {
        "role": "user",
        "content": "Explain API gateways in 2 sentences."
      }
    ],
    "maxTokens": 256
  }),
});
const { data } = await res.json();
console.log(data.message.content);

Why use Step 3.5 Flash through YepAPI?

One API key for all models — no separate accounts
OpenAI SDK compatible — just change the base URL
No monthly minimums — pay per token
Switch models with one line of code
Full provider passthrough — citations, search results, and all extras included
Streaming and non-streaming support on every model
Works with Cursor, Claude, LangChain, and any LLM tool
Unified billing across all providers

Step 3.5 Flash API: StepFun's fast, budget model

Step 3.5 Flash is StepFun's fast-inference model, a budget-friendly option with strong Chinese-language ability and a 262K context window. YepAPI serves it through one OpenAI-compatible endpoint.

Your single YepAPI key also reaches DeepSeek, Claude, Grok, Gemini, and more, plus SEO, SERP, and scraping endpoints, so Step 3.5 Flash can sit alongside your search and data tools.

What is Step 3.5 Flash?

Step 3.5 Flash is a fast-inference model from StepFun, a Chinese AI provider. It is built for speed and low cost on high-throughput workloads, with a 262,144-token context window and up to 65,536 output tokens. Its defining strengths are budget pricing and strong Chinese-language understanding, alongside broader multilingual capability, which makes it a good fit for applications serving Chinese-speaking users or working with Chinese-language content. As a Flash-tier model it prioritizes responsiveness and affordability over the deepest reasoning, suiting classification, translation, and routine generation at volume.

Build with Step 3.5 Flash via YepAPI

Use YepAPI's OpenAI-compatible /v1/ai/chat endpoint with any OpenAI client. Set the base URL, add your key, and set the model string to Step 3.5 Flash; your existing messages and parameters carry over. Switching models is a single string change. Because one key reaches the full catalog, you can route Chinese-language and high-volume tasks to Step 3.5 Flash and other work to different models, all from a single integration.

Step 3.5 Flash API pricing — $0.14 input / $0.42 output per 1M tokens

Step 3.5 Flash costs $0.14 per 1M input tokens and $0.42 per 1M output tokens, putting it firmly in budget territory. At these rates, high-volume translation, classification, and generation jobs stay inexpensive, and the 262K context window means you can include long inputs without changing the cost model. Per-token billing keeps large batch runs predictable.

Step 3.5 Flash for Chinese-language and multilingual tasks

Step 3.5 Flash is a strong choice when your workload centers on Chinese content or mixed multilingual text, translation, localization, classification, and generation for Chinese-speaking audiences. Its 262K context handles long documents, its Flash tuning keeps responses fast, and the low price makes it practical to run these tasks at scale, especially for products targeting Chinese markets that need a cost-efficient, locally strong model.

Try Step 3.5 Flash free

New YepAPI accounts come with $5 in free credit and no card required. That covers plenty of Step 3.5 Flash usage, enough to test its Chinese-language and multilingual quality on your own data, compare it with other models on the same key, and confirm fit before adding any payment method.

Start generating in 30 seconds

$5 free credit on signup. No credit card required. Pay per call.

What developers say

Switched from SerpAPI and cut our SERP costs by 80%. Same data quality, way simpler billing.

Marcus T.

SEO Platform Founder

One API key for AI models, SERP data, and web scraping. Saved us from managing 4 separate providers.

Priya S.

Full-Stack Developer

The $5 free credit let us prototype our entire rank tracking feature before committing. No other API does that.

Jake R.

Indie Hacker

Frequently asked questions

StepFun's fast inference model. Budget-friendly Chinese provider with 262K context window.

Input tokens cost $0.14 per 1M tokens and output tokens cost $0.42 per 1M tokens through YepAPI. No monthly minimums — you only pay for what you use.

Sign up for a free API key, then send requests to the /v1/ai/chat endpoint.

Step 3.5 Flash supports a 262K token context window with up to 66K output tokens per request.

Ready to use Step 3.5 Flash?

$5 free credit on signup. No credit card required. Pay per call.

Explore more models